Model Router

import openai

# Configure with your Hypermode Workspace API key and Hypermode Model Router base url
client = openai.OpenAI(
    api_key="<YOUR_HYP_WKS_KEY>",
    base_url="https://models.hypermode.host/v1",
)

# Set up the request
response = client.chat.completions.create(
    model="meta-llama/llama-4-scout-17b-16e-instruct",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Modus?"},
    ],
    max_tokens=150,
    temperature=0.7,
)

# Print the response
print(response.choices[0].message.content)

curl -X POST \
  https://models.hypermode.host/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_HYP_WKS_KEY" \
  -d '{
    "model": "meta-llama/llama-4-scout-17b-16e-instruct",
    "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is Dgraph?"}
    ],
    "max_tokens": 150,
    "temperature": 0.7
  }'

# Note: verify that your model supports the dimensions parameter
# this is the case for OpenAI 'text-embedding-3' and later models.

curl -X POST \
  https://models.hypermode.host/v1/embeddings \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_HYP_WKS_KEY" \
  -d '{
    "model": "text-embedding-3-large",
    "dimensions": 256,
    "input": [
        "Hypermode is an AI development platform that provides hosting and management capabilities for agents and knowledge graphs",
        "Modus is an open source, serverless framework for building functions and APIs, powered by WebAssembly."
    ],
    "encoding_format": "float"
  }'